例子:
>>> convert('CamelCase')
'camel_case'
例子:
>>> convert('CamelCase')
'camel_case'
当前回答
简洁,没有正则表达式,但HTTPResponseCode=> httpresponse_code:
def from_camel(name):
"""
ThisIsCamelCase ==> this_is_camel_case
"""
name = name.replace("_", "")
_cas = lambda _x : [_i.isupper() for _i in _x]
seq = zip(_cas(name[1:-1]), _cas(name[2:]))
ss = [_x + 1 for _x, (_i, _j) in enumerate(seq) if (_i, _j) == (False, True)]
return "".join([ch + "_" if _x in ss else ch for _x, ch in numerate(name.lower())])
其他回答
这不是一个优雅的方法,是一个非常“低级”的实现一个简单的状态机(位域状态机),可能是最反python模式来解决这个问题,然而re模块也实现了一个太复杂的状态机来解决这个简单的任务,所以我认为这是一个很好的解决方案。
def splitSymbol(s):
si, ci, state = 0, 0, 0 # start_index, current_index
'''
state bits:
0: no yields
1: lower yields
2: lower yields - 1
4: upper yields
8: digit yields
16: other yields
32 : upper sequence mark
'''
for c in s:
if c.islower():
if state & 1:
yield s[si:ci]
si = ci
elif state & 2:
yield s[si:ci - 1]
si = ci - 1
state = 4 | 8 | 16
ci += 1
elif c.isupper():
if state & 4:
yield s[si:ci]
si = ci
if state & 32:
state = 2 | 8 | 16 | 32
else:
state = 8 | 16 | 32
ci += 1
elif c.isdigit():
if state & 8:
yield s[si:ci]
si = ci
state = 1 | 4 | 16
ci += 1
else:
if state & 16:
yield s[si:ci]
state = 0
ci += 1 # eat ci
si = ci
print(' : ', c, bin(state))
if state:
yield s[si:ci]
def camelcaseToUnderscore(s):
return '_'.join(splitSymbol(s))
splitsymbol可以解析所有的大小写类型:UpperSEQUENCEInterleaved, under_score, BIG_SYMBOLS和cammelCasedMethods
我希望它是有用的
这个网站上提出了非常好的RegEx:
(?<!^)(?=[A-Z])
如果python有一个字符串分割方法,它应该工作…
在Java中:
String s = "loremIpsum";
words = s.split("(?<!^)(?=[A-Z])");
一个使用正则表达式的可怕例子(你可以很容易地清理:)):
def f(s):
return s.group(1).lower() + "_" + s.group(2).lower()
p = re.compile("([A-Z]+[a-z]+)([A-Z]?)")
print p.sub(f, "CamelCase")
print p.sub(f, "getHTTPResponseCode")
但适用于getHTTPResponseCode !
或者,使用lambda:
p = re.compile("([A-Z]+[a-z]+)([A-Z]?)")
print p.sub(lambda x: x.group(1).lower() + "_" + x.group(2).lower(), "CamelCase")
print p.sub(lambda x: x.group(1).lower() + "_" + x.group(2).lower(), "getHTTPResponseCode")
编辑:对于像“Test”这样的情况,应该也很容易看到有改进的空间,因为下划线是无条件插入的。
就我个人而言,我不确定在python中使用正则表达式的任何东西都可以被描述为优雅。这里的大多数答案只是做“代码高尔夫”类型的RE技巧。优雅的编码应该是容易理解的。
def to_snake_case(not_snake_case):
final = ''
for i in xrange(len(not_snake_case)):
item = not_snake_case[i]
if i < len(not_snake_case) - 1:
next_char_will_be_underscored = (
not_snake_case[i+1] == "_" or
not_snake_case[i+1] == " " or
not_snake_case[i+1].isupper()
)
if (item == " " or item == "_") and next_char_will_be_underscored:
continue
elif (item == " " or item == "_"):
final += "_"
elif item.isupper():
final += "_"+item.lower()
else:
final += item
if final[0] == "_":
final = final[1:]
return final
>>> to_snake_case("RegularExpressionsAreFunky")
'regular_expressions_are_funky'
>>> to_snake_case("RegularExpressionsAre Funky")
'regular_expressions_are_funky'
>>> to_snake_case("RegularExpressionsAre_Funky")
'regular_expressions_are_funky'
简洁,没有正则表达式,但HTTPResponseCode=> httpresponse_code:
def from_camel(name):
"""
ThisIsCamelCase ==> this_is_camel_case
"""
name = name.replace("_", "")
_cas = lambda _x : [_i.isupper() for _i in _x]
seq = zip(_cas(name[1:-1]), _cas(name[2:]))
ss = [_x + 1 for _x, (_i, _j) in enumerate(seq) if (_i, _j) == (False, True)]
return "".join([ch + "_" if _x in ss else ch for _x, ch in numerate(name.lower())])